INDEX

Explanations

occurrences of specific letters and acronyms within the text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

reb

-0.14

.life

-0.14

ittest

-0.14

Ð°Ð½Ð¸Ð¹

-0.14

alar

-0.14

 Kemal

-0.13

Thy

-0.13

rl

-0.13

xa

-0.13

 Hlav

-0.13

POSITIVE LOGITS

esseract

0.16

0.14

uster

0.14

æĭĽ

0.14

ãĥĥãĥĪ

0.14

NU

0.14

ayne

0.14

 ãĥ»

0.13

odal

0.13

uns

0.13

Activations Density 0.106%

occurrences of specific letters and acronyms within the text

No Comments

No Known Activations